© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 38222
    Prev
    Next
    INDEX
    Explanations

    perceptions

    np_max-act · gemini-2.0-flash

    This neuron responds to words about perception or the act of perceiving (e.g., “perceive,” “perception,” “perceived”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     terminology
    -0.06
     회원
    -0.06
     ва
    -0.06
    룹
    -0.06
    	btn
    -0.06
    <class
    -0.06
    ключ
    -0.06
    quir
    -0.06
     srdce
    -0.06
    (struct
    -0.06
    POSITIVE LOGITS
     *\
    0.07
     Aub
    0.07
    abar
    0.07
     Sacramento
    0.07
     стоимость
    0.06
    ظٹ
    0.06
    omin
    0.06
    _DOWNLOAD
    0.06
     IE
    0.06
    .surname
    0.06
    Activations Density 0.039%

    No Known Activations